爬取全国各地区汽车销量情况并⽤中国地图可视化展⽰
项⽬介绍
pyecharts 是Python制图⼀个功能⾮常强⼤的第三⽅库，不仅可以做简单的图表，还可以做世界地图，数据⼤屏等等，有兴趣的可以看⼀下官⽅⽂档。
⽹页详情
查看页⾯情况，由于页⾯没有采⽤JavaScript编写，因此我们直接就采⽤requests库进⾏内容爬取。
⽼规矩，F12 查看⽹页源码情况：
在Network选择框中获取⽹页的请求头：
headers_ ={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36 Edg /90.0.818.51"}
直接通过selecter选择器爬取想要的内容:
province = bs.select(" table > tbody > tr > td:nth-child(1)")
values = bs.select("table > tbody > tr > td:nth-child(2)")
代码
爬取数据代码
import requests
import re
from bs4 import BeautifulSoup
headers_ ={"User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/90.0.4430.93 Safari/537.36 Edg /90.0.818.51"}
url ='www.daas-auto/newsDe/892.html'
一汽丰越html = (url,headers = headers_)
bs =,"html.parser")
# print(bs)
province = bs.select(" table > tbody > tr > td:nth-child(1)")
values = bs.select("table > tbody > tr > td:nth-child(2)")
data =[]
for pro,val in zip(province,values):
d =[]沪昆高速车祸
w =
#由于Map可视化中国地图中，对于各个省份的命名是有固定的格式的，
#因此我们要对爬取的省份名称进⾏处理⼀下，详细情况可以看上⽂提到的pyecharts官⽅⽂档
if w =="省份":
w = w.replace("省份","地区")
else:
w = w.replace("省","")
w = w.replace("市","")
w = w.replace("⾃治区","")
w = w.replace("⼴西壮族","⼴西")
w = w.replace("新疆维吾尔","新疆")
w = w.replace("宁夏回族","宁夏")
d.append(w)
!='销量（辆）':
d.append())
else:
d.)上海学车费用
print(d)
data.append(d)
将爬取的数据保存到⽂档中
import xlwt #进⾏excel操作
#创建⼀个Excel数据表
word = xlwt.Workbook(encoding ='utf-8', style_compression=0)
# 添加sheet表格，并允许重复修改
sheet = word.add_sheet('销量数据', cell_overwrite_ok=True)
for i in range(0,len(data)):
d = data[i]
for j in range(0,2): #i,j均是从0开始的
sheet.write(i, j, d[j]) #第i+1⾏第j+1列，填⼊数据d[j]
word.save('销量数据.xls')
print("数据保存成功！")
中国地图可视化
from pyecharts.charts import Map
from pyecharts import options as opts
from pyecharts.globals import ThemeType, CurrentConfig
import pandas as pd
data = pd.read_excel("销量数据.xls")
# print(data['地区'])
# print(data['销量（辆）'])
datas =[(i, j)for i, j in zip(data['地区'], data['销量（辆）'])]
# 实例化⼀个Map对象
map_ =Map(init_opts=opts.InitOpts(theme=ThemeType.PURPLE_PASSION))
轿车排名# 地图 maptype="china"选择中国地图，data_pair=datas数据源
map_.add(series_name="销售数量", data_pair=datas, maptype="china")
525# 设置系列配置项
map_.set_series_opts(label_opts=opts.LabelOpts(is_show=False)) # 不显⽰label
# 设置全局配置项
map_.set_global_opts(
title_opts=opts.TitleOpts(title="各省份汽车销售情况",
pos_left='40%',
赛拉图轮胎pos_top='10'), # 调整title位置
legend_opts=opts.LegendOpts(is_show=False),
visualmap_opts=opts.VisualMapOpts(
max_=1450000,
min_=50000,
is_piecewise=True,
pieces=[{"max":250000,"min":50000,"label":"50000-250000","color":"#00FFFF"}, {"max":450000,"min":250001,"label":"250001-450000","color":"#FF69B4"},
{"max":650000,"min":450001,"label":"450001-650000","color":"#0000FF"},
{"max":850000,"min":650001,"label":"650001-850000","color":"#00BFFF"},
{"max":1050000,"min":850001,"label":"850001-1050000","color":"#228B22"},
{"max":1250000,"min":1050001,"label":"1050001-1250000","color":"#FF0000"},
{"max":1450000,"min":1250001,"label":">=1250001","color":"#FFD700"}
] # 分段添加图例注释和颜⾊
)
)
# 渲染在⽹页上有交互性
map_.render('各省份汽车销售情况.html')
map_.render_notebook()
运⾏效果
上个星期都没有更新博⽂，五⼀假期后的第⼀天继续努⼒！
结束，拜拜
发布评论